Abstract
Person re-identification (Re-ID) has achieved great success in single-domain. However, it remains a challenging task to adapt a Re-ID model trained on one dataset to another one. Unsupervised domain adaption (UDA) was proposed to migrate a model from a labeled source domain to an unlabeled target domain. The main difference in the cross-domain is different background styles. Although the style transfer approach effectively reduces inter-domain gaps, it ignores the reduction of intra-class differences. Clustering-based pipelines maintain state-of-the-art performance for UDA by learning domain-independent features; however, most existing models do not sufficiently exploit the rich unlabeled samples in target domains due to unsatisfactory clustering. Thus, we propose a novel local correlation ensemble model that focuses on the diversity of intra-class information and the reliability of class centers. Specifically, a pedestrian attention module is proposed to enable the encoder to pay more attention to the person’s features to relieve interference caused by the shared background style. Furthermore, we propose a priority-distance graph convolutional network (PDGCN) module that employs a graph convolutional network network to predict the priority of a node as a class center and then calculates the distance between nodes with high priority values to screen out the class center nodes. Finally, the encoder features (local) and PDGCN features (context-aware) are combined to perform person Re-ID. The results of experiments on the large-scale public Re-ID datasets verified the effectiveness of the proposed method.
- [1] . 2009. A comparison of extrinsic clustering evaluation metrics based on formal constraints. Inf. Retriev. 12, 4 (2009), 461–486.Google Scholar
Digital Library
- [2] . 2019. GCNet: Non-local networks meet squeeze-excitation networks and beyond. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19) Workshops.Google Scholar
Cross Ref
- [3] . 2019. Mixed high-order attention network for person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19). 371–381.Google Scholar
Cross Ref
- [4] . 2019. Instance-guided context rendering for cross-domain person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [5] . 2019. Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 257–266.Google Scholar
Digital Library
- [6] . 2021. Dual-refinement: Joint label and feature refinement for unsupervised domain adaptive person re-identification. IEEE Trans. Image Process. 30 (2021), 7815–7829.Google Scholar
- [7] . 2021. Cluster contrast for unsupervised person re-identification. arXiv:2103.11568. Retrieved from https://arxiv.org/abs/2103.11568.Google Scholar
- [8] . 2018. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [9] . 2018. Unsupervised person re-identification: Clustering and fine-tuning. ACM Trans. Multimedia Comput. Commun. Appl. 14, 4 (2018), 1–18.Google Scholar
Digital Library
- [10] . 2019. Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [11] . 2020. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In Proceedings of the 8th International Conference on Learning Representations (ICLR’20).Google Scholar
- [12] . 2020. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In Advances in Neural Information Processing Systems.Google Scholar
- [13] . 2018. Squeeze-and-excitation networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’18). 7132–7141.Google Scholar
Cross Ref
- [14] . 2021. PH-GCN: Person retrieval with part-based hierarchical graph convolutional network. IEEE Transactions on Multimedia.
DOI: Google ScholarDigital Library
- [15] . 2020. Style normalization and restitution for generalizable person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
Cross Ref
- [16] . 1998. A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20, 1 (1998), 359–392.Google Scholar
Digital Library
- [17] . 2019. Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [18] . 2018. Adaptation and re-identification network: An unsupervised deep transfer learning approach to person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18) Workshops.Google Scholar
Cross Ref
- [19] . 2013. POP: Person re-identification post-rank optimisation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’13).Google Scholar
Digital Library
- [20] . 2020. A strong baseline and batch normalization neck for deep person re-identification. IEEE Trans. Multimedia 22, 10 (2020), 2597–2609.Google Scholar
- [21] . 2019. AlignedReID++: Dynamically matching local information for person re-identification. Pattern Recogn. 94 (2019), 53–61.Google Scholar
Digital Library
- [22] . 2020. Unsupervised domain adaptation in the dissimilarity space for person re-identification. In Proceedings of the European Conference on Computer Vision (ECCV’20). Springer, 159–174.Google Scholar
Digital Library
- [23] . 2019. Pose-guided feature alignment for occluded person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19). 542–551.Google Scholar
Cross Ref
- [24] . 2022. AAGCN: Adjacency-aware graph convolutional network for person re-identification. Knowl.-Bas. Syst. 236 (2022), 107300.Google Scholar
Digital Library
- [25] . 2019. A novel unsupervised camera-aware domain adaptation framework for person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [26] . 2017. 3d graph neural networks for rgbd semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’17). 5199–5208.Google Scholar
Cross Ref
- [27] . 2021. Pseudo graph convolutional network for vehicle ReID. In Proceedings of the 29th ACM International Conference on Multimedia. 3162–3171.Google Scholar
Digital Library
- [28] . 2016. Performance measures and a data set for multi-target, multi-camera tracking. In Proceedings of the European Conference on Computer Vision (ECCV’16). Springer, 17–35.Google Scholar
Cross Ref
- [29] . 2014. Clustering by fast search and find of density peaks. Science 344, 6191 (2014), 1492–1496.Google Scholar
- [30] . 2019. A supervised learning to index model for approximate nearest neighbor image retrieval. Sign. Process.: Image Commun. 78, 10 (2019), 494–502.Google Scholar
- [31] . 2020. Metric learning-based kernel transformer with triplets and label constraints for feature fusion. Pattern Recogn. 99, (2020), 107086.Google Scholar
- [32] . 2020. Unsupervised domain adaptive re-identification: Theory and practice. Pattern Recogn, 102 (2020), 107173.Google Scholar
- [33] . 2019. Dissecting person re-identification from the viewpoint of viewpoint. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19). 608–617.Google Scholar
Cross Ref
- [34] . 2018. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European Conference on Computer Vision (ECCV’18). 480–496.Google Scholar
Digital Library
- [35] . 2010. Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance. J. Mach. Learn. Res. 11 (2010), 2837–2854.Google Scholar
Digital Library
- [36] . 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
Cross Ref
- [37] . 2018. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [38] . 2018. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’18).Google Scholar
Cross Ref
- [39] . 2018. CBAM: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV’18).Google Scholar
Digital Library
- [40] . 2019. Unsupervised person re-identification by camera-aware similarity consistency learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19). 6922–6931.Google Scholar
Cross Ref
- [41] . 2019. Progressive learning for person re-identification with one example. IEEE Trans. Image Process. 28, 6 (2019), 2872–2881.Google Scholar
Cross Ref
- [42] . 2020. Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization. IEEE Trans. Multimedia 23 (2020), 597–610.Google Scholar
Digital Library
- [43] . 2020. Learning to cluster faces via confidence and connectivity estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
Cross Ref
- [44] . 2019. Patch-based discriminative feature learning for unsupervised person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19).Google Scholar
Cross Ref
- [45] . 2020. Unsupervised person re-identification by soft multilabel learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
- [46] . 2020. AD-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20).Google Scholar
Cross Ref
- [47] . 2019. Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’19).Google Scholar
Cross Ref
- [48] . 2020. PGAN: Part-based nondirect coupling embedded GAN for person reidentification. IEEE MultiMedia 27, 3 (2020), 23–33.Google Scholar
Digital Library
- [49] . 2021. Exploiting sample uncertainty for domain adaptive person re-identification. In Proceedings of the Association for the Advance of Artificial Intelligence (AAAI’21).Google Scholar
Cross Ref
- [50] . 2015. Scalable person re-identification: A benchmark. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV’15). 1116–1124.Google Scholar
Cross Ref
- [51] . 2018. Generalizing a person retrieval model hetero- and homogeneously. In Proceedings of the European Conference on Computer Vision (ECCV’18).Google Scholar
Digital Library
- [52] . 2019. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19). 598–607.Google Scholar
Cross Ref
- [53] . 2020. Learning to adapt invariance in memory for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 8 (2020), 2723–2738.Google Scholar
Index Terms
Local Correlation Ensemble with GCN Based on Attention Features for Cross-domain Person Re-ID
Recommendations
Unsupervised Cross-Domain Person Re-identification Based on Style Transfer
Intelligent Computing Theories and ApplicationAbstractPerson re-identification (person Re-ID) is mostly viewed as an image retrieval problem across different cameras. Most of existing models have achieved significant improvement on single-domain setting but failed to generalize to new domain due to ...
Self-Supervised Pre-training on the Target Domain for Cross-Domain Person Re-identification
MM '21: Proceedings of the 29th ACM International Conference on MultimediaMost existing cluster-based cross-domain person re-identification (re-id) methods only pre-train the re-id model on the source domain. Unfortunately, the pre-trained model may not perform well on the target domain due to the large domain gap between ...
Cross-domain Person Re-identification Based on the Sample Relation Guidance
Image and GraphicsAbstractThe existing mainstream cross-domain person re-identification (Re-ID) methods mainly focus on reducing the deviation of the generated pseudo labels, and they did not introduce veracious label information for algorithm training on the unlabeled ...






Comments